New-Pytorch-Chinese:中文文本摘要,基于pytorch,采用LCSTS数据集-源码

上传者: 42153793 | 上传时间: 2021-06-27 09:50:04 | 文件大小: 8.84MB | 文件类型: ZIP
基于Pytorch的中文文本摘要生成 开这个仓库的主要目的是记录一下自己实验过程和数据。 参考文本摘要领域大佬写的两篇论文: and ,然后参考另一位大佬修改的代码. 另外,在这里还是要感谢一下。这里的所有内容基本上没做什么修改(python读取文件的时候出现编码问题,我的猜想是大佬用的mac系统,类linux,所以对编码不敏感,我用windows的话就报错了。),最多修改了一下超参数,刚开始在自己windows笔记本上跑的话,确实有点吃力,设置的batch_size=10,好像后来还直接报cuda错误,我的猜想就是设置过大了,显存承受不了。说多了。直接看训练和测试效果吧。 实验结果 指标 验证集 测试集 ROUGE-1 34.06 31.87 ROUGE-2 16.46 15.47 ROUGE-L 33.83 30.93 0. 数据预处理 下载(提取码:g8c6 ),下载完之后放在根目

文件下载

资源详情

[{"title":"( 43 个子文件 8.84MB ) New-Pytorch-Chinese:中文文本摘要,基于pytorch,采用LCSTS数据集-源码","children":[{"title":"New-Pytorch-Chinese-master","children":[{"title":"vocab <span style='color:#111;'> 601.60KB </span>","children":null,"spread":false},{"title":".dockerignore <span style='color:#111;'> 37B </span>","children":null,"spread":false},{"title":"eval.sh <span style='color:#111;'> 138B </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 16.51KB </span>","children":null,"spread":false},{"title":".github","children":[{"title":"workflows","children":[{"title":"python-app.yml <span style='color:#111;'> 1.15KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"train_rl.sh <span style='color:#111;'> 118B </span>","children":null,"spread":false},{"title":"data_util","children":[{"title":"logs","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false}],"spread":true},{"title":"config.py <span style='color:#111;'> 706B </span>","children":null,"spread":false},{"title":"batcher.py <span style='color:#111;'> 15.07KB </span>","children":null,"spread":false},{"title":"data.py <span style='color:#111;'> 7.82KB </span>","children":null,"spread":false},{"title":"log.py <span style='color:#111;'> 837B </span>","children":null,"spread":false}],"spread":true},{"title":"web.py <span style='color:#111;'> 1.24KB </span>","children":null,"spread":false},{"title":"ci-test","children":[{"title":"test.py <span style='color:#111;'> 156B </span>","children":null,"spread":false},{"title":"test_case.py <span style='color:#111;'> 34B </span>","children":null,"spread":false}],"spread":true},{"title":"requirements-ci.txt <span style='color:#111;'> 46B </span>","children":null,"spread":false},{"title":"ci-test.sh <span style='color:#111;'> 49B </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 8.24KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 77B </span>","children":null,"spread":false},{"title":"dockerfile <span style='color:#111;'> 491B </span>","children":null,"spread":false},{"title":".idea","children":[{"title":"misc.xml <span style='color:#111;'> 200B </span>","children":null,"spread":false},{"title":"New-Pytorch-Chinese.iml <span style='color:#111;'> 798B </span>","children":null,"spread":false},{"title":"encodings.xml <span style='color:#111;'> 202B </span>","children":null,"spread":false},{"title":"inspectionProfiles","children":[{"title":"Project_Default.xml <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"profiles_settings.xml <span style='color:#111;'> 174B </span>","children":null,"spread":false}],"spread":false},{"title":"deployment.xml <span style='color:#111;'> 560B </span>","children":null,"spread":false},{"title":"modules.xml <span style='color:#111;'> 290B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 223B </span>","children":null,"spread":false},{"title":"vcs.xml <span style='color:#111;'> 180B </span>","children":null,"spread":false}],"spread":false},{"title":"train.sh <span style='color:#111;'> 75B </span>","children":null,"spread":false},{"title":"train_util.py <span style='color:#111;'> 1.46KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"eval.py <span style='color:#111;'> 7.21KB </span>","children":null,"spread":false},{"title":"beam_search.py <span style='color:#111;'> 8.26KB </span>","children":null,"spread":false},{"title":"test.sh <span style='color:#111;'> 64B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 23.61KB </span>","children":null,"spread":false},{"title":"requirements-web.txt <span style='color:#111;'> 96B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"vocab <span style='color:#111;'> 583.97KB </span>","children":null,"spread":false},{"title":"test_0705000.txt <span style='color:#111;'> 39.37KB </span>","children":null,"spread":false},{"title":"all_vocab.txt <span style='color:#111;'> 17.01MB </span>","children":null,"spread":false}],"spread":false},{"title":"test_web.py <span style='color:#111;'> 550B </span>","children":null,"spread":false},{"title":"docker-compose.yml <span style='color:#111;'> 287B </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 153B </span>","children":null,"spread":false},{"title":"make_data_files.py <span style='color:#111;'> 6.64KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

免责申明

【只为小站】的资源来自网友分享,仅供学习研究,请务必在下载后24小时内给予删除,不得用于其他任何用途,否则后果自负。基于互联网的特殊性,【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查;无论 【只为小站】 经营者是否已进行审查,用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场,基于网友分享,根据中国法律《信息网络传播权保护条例》第二十二条之规定,若资源存在侵权或相关问题请联系本站客服人员,zhiweidada#qq.com,请把#换成@,本站将给予最大的支持与配合,做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明